Cool result by @furongh @btreetaiji on how #tensor methods help explain good generalization in #DeepLearning My 1 slide summary. Layers in neural network are more compressible when tensorized. This gives tighter generalization that agrees with observed test error https://twitter.com/furongh/status/1214374436134162432 …pic.twitter.com/AZT9XWEgwX
2:27 PM - 22 Jan 2020
0 replies
19 retweets
69 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.